EvilPort2/Sign-Language
A very simple CNN project to recognize gestures made in American Sign Language
Implements a complete pipeline for capturing custom ASL gesture datasets (1200 images per gesture at 50x50 grayscale), training CNN models via TensorFlow or Keras with MNIST-like architecture, and performing real-time inference on video streams using skin-color histogram segmentation. Includes utilities for data augmentation (vertical flipping), model evaluation with confusion matrices and precision/recall metrics, and integrates pyttsx3 for audio feedback during gesture recognition.
818 stars. No commits in the last 6 months.
Stars
818
Forks
359
Language
—
License
—
Category
Last pushed
Aug 07, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/EvilPort2/Sign-Language"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
harshbg/Sign-Language-Interpreter-using-Deep-Learning
A sign language interpreter using live video feed from the camera.
AvishakeAdhikary/Realtime-Sign-Language-Detection-Using-LSTM-Model
Realtime Sign Language Detection: Deep learning model for accurate, real-time recognition of...
beingaryan/Sign-To-Speech-Conversion
Sign Language Detection system based on computer vision and deep learning using OpenCV and...
Arshad221b/Sign-Language-Recognition
Indian Sign language Recognition using OpenCV
Tachionstrahl/SignLanguageRecognition
Real-time Recognition of german sign language (DGS) with MediaPipe